xxradon / ONNXToCaffe

pytorch -> onnx -> caffe, pytorch to caffe, or other deep learning framework to onnx and onnx to caffe.
158 stars 33 forks source link

转换caffe报错Check failed: bottom[i]->shape() == bottom[0]->shape() #18

Open michaelmo666 opened 2 years ago

michaelmo666 commented 2 years ago

在将pytorch的DDRNet转换为caffe的时候报了如下错误:

F0222 06:37:17.979665 24253 eltwise_layer.cpp:34] Check failed: bottom[i]->shape() == bottom[0]->shape()

输入大小为[1,3,512,1024]应该是在upsample层出现了问题,其中有一个upsample是bilinear的 height_scale=8, width_scale=16;看到在_operators.py_convert_upsample 将 height_scale=width_scale=2;我将这里注释掉了,并且在下面改为Deconv中的stride_w也该成了width_scale; 但依旧报错,希望可以指导一下

2239891257 commented 1 year ago

你好,请问解决了吗? 我也出现相同问题